"Computer Science - Machine Learning"

ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to …
Cite PDF html arXiv Poster Thread GitHub NeurIPS 2023
ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
Latent Space Translation via Semantic Alignment
Different neural models often exhibit similar latent spaces when exposed to semantically similar data; however, this inherent …
Cite PDF URL GitHub
Latent Space Translation via Semantic Alignment
Spectral Maps for Learning on Subgraphs
In graph learning, maps between graphs and their subgraphs frequently arise. For instance, when coarsening or rewiring operations are …
PDF Cite URL PDF Best Paper Award
Spectral Maps for Learning on Subgraphs
Learning Spectral Unions of Partial Deformable 3D Shapes
Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study …
PDF Cite URL
Learning Spectral Unions of Partial Deformable 3D Shapes
Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach
Many natural shapes have most of their characterizing features concentrated over a few regions in space. For example, humans and …
PDF Cite URL GitHub
Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach